Val-LLM: A Visual Analytics Approach for the Critical Validation of LLM-Generated Tabular Data

dc.contributor.authorSachdeva, Madhaven_US
dc.contributor.authorNarayanan, Christopheren_US
dc.contributor.authorWiedenkeller, Marvinen_US
dc.contributor.authorSedlakova, Janaen_US
dc.contributor.authorBernard, Jürgenen_US
dc.contributor.editorEgger, Bernharden_US
dc.contributor.editorGünther, Tobiasen_US
dc.date.accessioned2025-09-24T10:37:27Z
dc.date.available2025-09-24T10:37:27Z
dc.date.issued2025
dc.description.abstractLarge Language Models (LLMs) are emerging as promising approaches for tabular data generation and enrichment, helping to ease constraints related to data availability. However, the reliable use of LLM-generated data remains challenging, e.g., due to hallucinations and inconsistencies. While some validation approaches exist, five key challenges remain: the lack of explanations and transparency in how values are generated, balancing fine-grained accurate with coarse-grained scalable validation, validating generated data without ground truth, and evaluating plausibility, semantic relevance, and downstream utility. To address these challenges, we present Val-LLM, a novel visual analytics approach for the critical validation of LLM-generated tabular data. Val-LLM enables users to contextualize generated data values with explanations, externalize human expert knowledge, relate LLM outputs with existing data, and assess the data utility in an application downstream. We conducted a user study to evaluate Val-LLM. Results highlight the usefulness of supporting multiple levels of granularity and enabling human knowledge externalization for validation. The study also indicates the need to study validation workflows and workflow flexibility, based on user domain experience and user preferences. Our work supports the trustworthy and effective use of LLM-generated tabular data by integrating visual analytics for systematic data validation.en_US
dc.description.sectionheadersVisualization, Visual Analytics, and VR
dc.description.seriesinformationVision, Modeling, and Visualization
dc.identifier.doi10.2312/vmv.20251235
dc.identifier.isbn978-3-03868-294-3
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/vmv.20251235
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/vmv20251235
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Human-centered computing → Interactive systems and tools; Visual analytics
dc.subjectHuman centered computing → Interactive systems and tools
dc.subjectVisual analytics
dc.titleVal-LLM: A Visual Analytics Approach for the Critical Validation of LLM-Generated Tabular Dataen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
vmv20251235.pdf
Size:
3.38 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
paper1044_3.pdf
Size:
5.02 MB
Format:
Adobe Portable Document Format
Collections